On Wed, May 5, 2021 at 2:12 PM Thomas Munro <thomas.munro@gmail.com> wrote:
> It might be interesting to know how that 40ms time scales as you add
> more workers. ...
Another thought: I'd also try tests like that in large databases (ie
large virtual memory) vs small ones, and with and without huge/locked
memory pages configured[1], to see how much of the overhead is due to
virtual memory work (though I know nothing about Windows VM, it's just
an idea).
[1] https://www.postgresql.org/docs/13/runtime-config-resource.html#GUC-HUGE-PAGES
